_1777370074079_638186083.jpg&w=64&q=75){kind=small}
Jiminay now offers voice cloning and realistic speech conversion
Google has announced two new versions of text-to-speech models: Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. They aim to deliver realistic voices with high control over audio performance. The technology allows for replicating a user's voice in just 30 seconds of voice recording, with the capability to create new voices through textual descriptions. It supports over 2,000 voices and more than 100 languages and dialects. The models feature the ability to adjust tone, speed, accent, and emotions of the voice, as well as support conversations between two characters. This makes them suitable for podcasts, audiobooks, dubbing, and gaming. Google is also implementing safeguards to prevent misuse by requiring consent from the original voice owner and embedding markers that identify generated content, promoting safe and trustworthy use.
تنويه: هذا ملخص تم إنشاؤه بواسطة الذكاء الاصطناعي
comments.heading